How to integrate Unify with Claude Code
To integrate Unify with Claude Code, add the unifygtm/agent-plugins marketplace and install unify@unify-plugins at user scope. Restart Claude Code, open /mcp, and complete Unify sign-in. The official plugin bundles Unify skills and MCP configuration so a terminal task can request sales research and track the resulting Agent run.[1][3]
- Connection
- Official MCP
- AI assistants
- Tool
- Claude Code
- Unify-documented client setup
- Data flow
- Claude Code ↔ Unify
- Tool calls and returned results
At a glance
- Use the Unify-documented Claude Code setup
- Use tool calls and returned results instead of an outbound Play payload
- Check the final Agent result before treating the task as complete
When this workflow makes sense
Start with the decision your team needs to make, then choose the connection that supports it.
The terminal is a useful home for repeatable operational work when the data access is explicit. A developer can ask for a narrow account review, save the completed output, and make the follow-up process reproducible. Keep the Unify run lifecycle visible: starting work and receiving a run ID is not the same as receiving its final results.
A good fit when
Developers and technical operators using Claude Code who need Unify context without building their own API client.
Reconsider the plan when
User-scope installation makes the plugin available across projects for that user. Confirm the connected Unify identity when switching work contexts, and do not copy credentials into repository files.
Design the handoff
Use this framework to agree on the input, the next action, and who owns the result.
Suggested workflow design, based on the documented capabilities below.
| Stage | Decision to make |
|---|---|
| Client and account | Claude Code installed, permission to add the official Unify marketplace, and a browser for Unify sign-in |
| First task | Suggested prompt: “Use Unify to research example.com. Track the Agent run to completion and save a concise account brief with the run ID. Do not enroll contacts or change records.” |
| Execution | Define whether the request is research-only or includes a specific authorized action. Keep the run ID for follow-up. |
| Result | Review the final output and unresolved questions before using the result in a sales decision. |
Explore the scenarios
Choose the situation that fits your team and work through the proposed plan.
Open a scenario to explore its plan. Checklists track your selections in this page only.
Save a research result for an operations task
A terminal task needs account context before producing an internal deliverable.
Read the completed Agent output before treating the research as input to the deliverable.
- Start one bounded research run
- Track its status and answer any clarification questions
- Save the final result with the run ID and unresolved questions
Recover an interrupted research session
The terminal session ended while Unify was still processing a task.
Find the existing run before starting duplicate work.
- Inspect recent Agent runs for the connected user
- Identify the original run and check its status
- Read its result or resolve its pending clarification
Illustrative workflow, not a preconfigured automation. Complete these checks in your own account.
Define success before launch
Inspect the data and the intended outcome separately. Connection status is only the first check.
Expected, not tested
After the connection is authorized, Claude Code can identify the intended Unify user and retrieve the completed output of the controlled research task.
Inspect get_me, the requested task, the final run status, and read_agent_results together. A discovered tool or a run ID confirms a different stage from a completed result. For any explicitly requested write, inspect the actual destination record as well.
Documentation-based reference. This workflow has not been tested end to end. Use a record or event you control before enabling live activity.
Questions answered
Common decisions when connecting Unify and Claude Code.
How do I connect Unify to Claude Code?
Run the two commands below to add Unify’s official marketplace and install the plugin at user scope. These commands configure the client; they do not execute a prospecting task.[1][3]
How do I check that Claude Code connected to Unify?
After installing and fully restarting Claude Code, run /mcp and complete the Unify login. Inspect the available tools, then check the authenticated identity before requesting Agent work.[1][2][3]
How is MCP different from a Play webhook?
An MCP client can invoke Unify tools and retrieve their documented results. The Play Webhook action sends an external request and does not pass its response into downstream Play steps. They are separate connection mechanisms.[2][5]
Does a run ID mean the task succeeded?
No. run_agent starts background work. Check the run with poll_agent, handle any clarification, and call read_agent_results after the run reaches READY or ERROR.[2]
Limits & decisions
Check these boundaries before designing a live workflow around the connection.
- User-scope installation makes the plugin available across projects for that user. Confirm the connected Unify identity when switching work contexts, and do not copy credentials into repository files.[1][3]
- Unify permissions and Agent usage limits still apply[1][2]
- A completed research result does not itself authorize sending, enrollment, or CRM updates
- No authenticated end-to-end execution has been performed
What the connection supports
Understand the connection, the data involved, and the behavior that matters for a Unify + Claude Code workflow.
The assistant requests work from Unify and retrieves its result using the connected user’s permissions.
| Decision | What to know |
|---|---|
| Connection route | Unify explicitly documents Claude Code setup[1] |
| Client requirement | Claude Code installed, permission to add the official Unify marketplace, and a browser for Unify sign-in[1][3] |
| Published server | https://mcp.unifygtm.com/mcp (authentication required)[4] |
| Identity | Calls are scoped to the authenticated Unify user and tenant[2] |
| Agent lifecycle | Start a run, poll status, answer clarification, and read the terminal result[2] |
| Usage | Unify MCP Agent work uses existing Unify Chat usage and credits[1] |
MCP exposes tool schemas to the client. For Agent work, provide a natural-language prompt and retain the returned runId for status and result calls. Direct API tools have their own required inputs. This connection is separate from a Play’s outbound Webhook action and does not make webhook responses available to later Play steps.
Technical setup reference
References and requirements for the Claude Code connection.
Connection requirements and setup checklist
Before connecting
- Claude Code installed, permission to add the official Unify marketplace, and a browser for Unify sign-in
- A Unify user with access to the intended workspace and available Chat credits for Agent runs
- One controlled research task with a clear output and explicit boundaries on record changes
Restart and sign in
Fully restart Claude Code, run /mcp, and complete Unify login when prompted. Use the official plugin configuration rather than inventing a server URL or an API-key header.[1]
Inspect identity and tools
Ask the client to inspect the Unify tools and call get_me. Compare the returned user and workspace with the account you intended to connect.[2]
Check the Agent result
For Agent work, run_agent returns a runId before the task finishes. Poll that run. Answer every returned question if its status is CLARIFICATION_NEEDED. On READY, read_agent_results returns the completed output; on ERROR, inspect the reported failure.[2]
Official Claude Code installation commands
claude plugin marketplace add unifygtm/agent-plugins --scope user
claude plugin install unify@unify-plugins --scope userRun these in your own terminal, then follow the sign-in steps.
Troubleshooting
Start with the stage where the expected data or action stops appearing.
The client cannot find or authorize Unify
Check the official installation path for this client, workspace policy, and required account connection. Restart clients where Unify’s setup calls for it, then repeat sign-in.[1][3]
A run starts but no result appears
Keep the original runId and poll its status. PENDING is still running; CLARIFICATION_NEEDED requires answers; READY permits reading the result. Use list_agent_runs to find a previous run rather than starting duplicate work.[2]
The tool reports missing access or unavailable credits
Verify the connected user and workspace. Unify scopes tools to that user, and Agent runs require available Chat funding and are subject to rate limits. A table owned by another user is not accessible through load_datatable.[2]
Sources & review
Official documentation reviewed on September 16, 2026.
Technical claims link to primary documentation from Unify and the destination tool. Scenarios, field choices, and recovery plans are editorial implementation examples. Documentation review is separate from execution testing.
Documentation reviewed; end-to-end execution not tested. No named technical reviewer has signed off on these articles yet.
Content updated: . Report a correction to Unify with the tool name, source URL, and behavior you observed.
Keep exploring
